Drug repositioning: a machine-learning approach through data integration

TLDR

Current drug‑repositioning methods rely mainly on cell‑line gene‑expression or drug‑disease links, but noisy data and limited genomic coverage hinder their effectiveness, while efficient repurposing could profoundly accelerate drug development. The study proposes a novel machine‑learning approach to predict drug repositioning. The method predicts therapeutic classes of FDA‑approved drugs using a drug‑centered model that integrates chemical similarity, target proximity in protein‑protein interaction networks, and correlated gene‑expression responses, without relying on disease data. The classifier achieved 78 % accuracy, enabling re‑classification of top mispredictions after rigorous statistical testing, and the approach could accelerate clinical translation of existing drugs for new therapeutic uses.

Abstract

: Existing computational methods for drug repositioning either rely only on the gene expression response of cell lines after treatment, or on drug-to-disease relationships, merging several information levels. However, the noisy nature of the gene expression and the scarcity of genomic data for many diseases are important limitations to such approaches. Here we focused on a drug-centered approach by predicting the therapeutic class of FDA-approved compounds, not considering data concerning the diseases. We propose a novel computational approach to predict drug repositioning based on state-of-the-art machine-learning algorithms. We have integrated multiple layers of information: i) on the distances of the drugs based on how similar are their chemical structures, ii) on how close are their targets within the protein-protein interaction network, and iii) on how correlated are the gene expression patterns after treatment. Our classifier reaches high accuracy levels (78%), allowing us to re-interpret the top misclassifications as re-classifications, after rigorous statistical evaluation. Efficient drug repurposing has the potential to significantly impact the whole field of drug development. The results presented here can significantly accelerate the translation into the clinics of known compounds for novel therapeutic uses.